Describing objects by their attributes
Ali Farhadi, Ian Endres, Derek Hoiem et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 2009
We propose to shift the goal of recognition from naming to describing. Doing so allows us not only to name familiar objects, but also: to report unusual aspects of a familiar object (“spotty dog”, not just “dog”); to say something about unfamiliar objects (“hairy and four-legged”, not just “unknown”); and to learn how to recognize new objects with few or no visual examples. Rather than focusing on identity assignment, we make inferring attributes the core problem of recognition. These attributes can be semantic (“spotty”) or discriminative (“dogs have it but sheep do not”). Learning attributes presents a major new challenge: generalization across object categories, not just across instances within a category. In this paper, we also introduce a novel feature selection method for learning attributes that generalize well across categories. We support our claims by thorough evaluation that provides insights into the limitations of the standard recognition paradigm of naming and demonstrates the new abilities provided by our attribute-based framework.
Cited by 1,827 works. doi:10.1109/cvpr.2009.5206772
Authors
References
- Histograms of Oriented Gradients for Human Detection
- Object class recognition by unsupervised scale-invariant learning
- Video Google: a text retrieval approach to object matching in videos
- The PASCAL visual object classes challenge 2006 (VOC2006) results
- A discriminatively trained, multiscale, deformable part model
- Basic objects in natural categories
- Multitask Learning
- Utility data annotation with Amazon Mechanical Turk
- Sharing features: efficient boosting procedures for multiclass object detection
- Learning to detect unseen object classes by between-class attribute transfer